Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dialogue or conversation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.80
     같
    0.79
    ב
    0.75
    0
    0.70
     Saltar
    0.68
     (
    0.68
     k
    0.66
     Перейти
    0.65
    0.65
    ke
    0.64
    POSITIVE LOGITS
     тысячи
    1.01
     monomials
    0.96
    стное
    0.94
     racionais
    0.94
    ontal
    0.93
    Desired
    0.92
    ඩ්
    0.89
    䛶
    0.89
    㖮
    0.89
    Fragments
    0.88
    Act Density 0.002%

    No Known Activations